LowEndBox - Cheap VPS, Hosting and Dedicated Server Deals

VPS Deploy - $6.99 768MB OpenVZ VPS with SSD in France

VPS Deploy VPS Deploy sent me this offer last week. They just had this new cluster going online in OVH in France with Intel SSD 320 drives, and they are providing recurring $2 off on their “Level 1” plan. Use promo code lowendssd to get the discount, or use this sign up link to order. It would be $6.99/month after the discount, and here is what you will get

  • 768MB guaranteed/1024MB burstable memory
  • 10GB storage on SSD
  • 500GB/month data transfer on 33Mbps
  • OpenVZ/SolusVM

They are using Xeon W3520 and Intel SSD 320-Series with no RAID but with daily backups, although daily backups should always still be users’ own responsibility. Here is one positive review on the performance of the VPS, and benchmark posted on their previous post also shows impressive disk IO. Spanish company with domain first registered in May 2010. No SSL on WHMCS, and offers only PayPal as payment method. Update: Test IP: 178.33.117.188, thanks to Kris.

LEA
Latest posts by LEA (see all)

36 Comments

  1. Why 33 mbps uplink? Is this some sort of a typo?

    July 26, 2011 @ 12:43 am | Reply
    • Probably artificially throttled to make higher end plans more appealing?

      July 26, 2011 @ 12:50 am | Reply
      • LOL. I think I would have to agree, seen the next plan with 66mb uplink and the rest is 100mbps uplink

        July 26, 2011 @ 5:08 am | Reply
  2. The test IP is ?

    July 26, 2011 @ 1:23 am | Reply
  3. Go:

    That’s what I call a revolutionary offer. SSD FTW! I would recommend this for someone running lets say a forum, over XEN VPS with same resources, hmmm, agree on that?!

    July 26, 2011 @ 1:58 am | Reply
  4. My review that was mentioned.

    For the exact box IP / test IP that was asked:

    ssd.cpq.is (178.33.117.188)

    -K, were.so

    July 26, 2011 @ 4:01 am | Reply
  5. The owner has admitted to using a RAID0, he seems to think i’m lying that SSD’s randomly just die.

    Francisco

    July 26, 2011 @ 4:07 am | Reply
    • Here is the reference, although I cannot confirm whether they are really using RAID0 on those new offers. Judging from the performance, as 320 series seems to cap write speed at around 200MB/sec, yes it would be likely that they use a strip to get the 300MB/sec figure.

      I guess we’ll see in the next 12 months on the reliability of this thing.

      July 26, 2011 @ 4:21 am | Reply
      • 12 months? Try a few weeks as TRIM is not supported in raid or ext3, GC cannot work as there is no idle time in raid, so a few weeks from now performs should degrade to a stand still.

        July 26, 2011 @ 8:23 am | Reply
        • Hi,
          yes, we use a RAID-0 config for our SSD VPS offer.
          In security terms, we do a daily vzdump in a remote FTP server with dual snap, in crash case, we can restore the last 12h backup or the last 36h backup.
          If you need a redundant service, you can do a constant rsync and syncronize your VPS data to other backup VPS, or run mysql-mmm or similar.
          If you need a cheap low cost and very speedy server, our offer is for you ;)
          Regards!

          July 26, 2011 @ 7:33 pm | Reply
        • @Tim Flavin , I have read all day about TRIM support in Linux. You have reason, we are working in a risk performance system. Anyway… we are working in a new cluster!! :)
          CentOS 6 + 2.6.32 + EXT4 is supported by OpenVZ and TRIM seems work… we will try, more info soon ;)

          Thanks for your comment :O

          July 28, 2011 @ 12:25 am | Reply
        • done! discard is not supported with RAID-0, but TRIM is enabled and not problems with noatime. Better performance in EXT4, 353 MB/s!!!

          Regards!!

          [root@cluster004 vz]# uname -a
          Linux cluster004.vpsdeploy.com 2.6.32-042stab024.1 #1 SMP Tue Jul 26 15:23:12 MSD 2011 x86_64 x86_64 x86_64 GNU/Linux
          [root@cluster004 vz]#
          [root@cluster004 vz]#
          [root@cluster004 vz]# hdparm -I /dev/sda | grep TRIM
          * Data Set Management TRIM supported
          * Deterministic read after TRIM
          [root@cluster004 vz]#
          [root@cluster004 vz]#
          [root@cluster004 vz]# cat /etc/fstab | grep ext4
          / ext4 noatime,discard,defaults 1 1
          /dev/mapper/vz-vz /vz ext4 noatime,discard,defaults 1 2
          [root@cluster004 vz]#
          [root@cluster004 vz]#
          [root@cluster004 vz]# dmesg | grep ext4
          [root@cluster004 vz]# dmesg | grep EXT4
          [ 4.652875] EXT4-fs (md0): mounted filesystem with ordered data mode
          [ 4.657863] EXT4-fs (md0): mounted filesystem with ordered data mode
          [ 5.502743] EXT4-fs (dm-0): mounted filesystem with ordered data mode
          [ 10.435771] EXT4-fs warning (device md0): release_blocks_on_commit: discard not supported, disabling
          [ 16.244111] EXT4-fs warning (device dm-0): release_blocks_on_commit: discard not supported, disabling
          [root@cluster004 vz]#
          [root@cluster004 vz]#
          [root@cluster004 vz]# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
          16384+0 records in
          16384+0 records out
          1073741824 bytes (1.1 GB) copied, 3.04529 s, 353 MB/s
          [root@cluster004 vz]#

          July 29, 2011 @ 11:41 pm | Reply
        • This will be very interesting to watch over time, as a quick search turned up nothing that shows mdadm and trim being supported.

          July 30, 2011 @ 1:31 am | Reply
        • I’m so waiting for this card to add support as it will probably be the first company to do so http://thessdreview.com/our-reviews/areca-1880ix-12-pcie-6g-sas-raid-controller-review-ssd-in-raid-0-lightning-strikes-at-3-6gbs/

          That is just stupid fast on a $900 raid card.

          July 30, 2011 @ 1:56 am | Reply
    • Go:

      But not only about read/write speed, but also improves performance, as physical read/write in HDD greatly reduce performance. I used an SSD in my old netbook, which loaded Windows faster than my laptop that was several times more powerful! Applications loading was amazing as well. That was with performance of a 3 years ago, 8GB SSD.

      However I can see the point of possibility of shortened life, or random die, when used in servers. Since if normal SSD is designed for home use to work for 5 years, then in a server used by 10 users 24h/7d, it is possible to wear out in 6 months! That is only if SSD wasn’t able to overcome limited life span in any recent models.

      July 26, 2011 @ 1:19 pm | Reply
    • How reliable are they? :)

      July 26, 2011 @ 9:22 pm | Reply
  6. shearerc:

    Nice offer, although I think SSD isn’t ready for prime-time production use yet…

    July 26, 2011 @ 10:20 am | Reply
  7. ConstB:

    … and it’s at OVH datacentre of course.

    July 26, 2011 @ 12:29 pm | Reply
  8. thl:

    they stole my business plan :<
    (ok only around 60-70% of it)

    July 26, 2011 @ 3:40 pm | Reply
  9. vedran:

    If would be nice to see some dd tests!

    July 26, 2011 @ 5:16 pm | Reply
    • iKocka:
      paris:~# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
      16384+0 records in
      16384+0 records out
      1073741824 bytes (1.1 GB) copied, 3.60382 s, 298 MB/s
      
      July 26, 2011 @ 5:50 pm | Reply
    • [root@cluster003 ~]# top | grep load
      top - 06:24:11 up 10 days,  6:24,  1 user,  load average: 6.68, 7.34, 6.75
      
      [root@cluster003 ~]# top | grep Cpu
      Cpu(s): 22.7%us,  7.5%sy,  0.3%ni, 66.6%id,  1.9%wa,  0.0%hi,  0.9%si,  0.0%st
      
      [root@cluster003 ~]# top | grep Tasks
      Tasks: 1723 total,   7 running, 1715 sleeping,   0 stopped,   1 zombie
      
      [root@cluster003 ~]# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
      16384+0 records in
      16384+0 records out
      1073741824 bytes (1.1 GB) copied, 6.87272 seconds, 156 MB/s
      [root@cluster003 ~]# rm -rf test
      [root@cluster003 ~]# cd /vz
      [root@cluster003 vz]# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
      16384+0 records in
      16384+0 records out
      1073741824 bytes (1.1 GB) copied, 3.47528 seconds, 309 MB/s
      [root@cluster003 vz]# echo 'Thanks LowEndBox!!! and regards for his community!!!'
      Thanks LowEndBox!!! and regards for his community!!!
      [root@cluster003 vz]#
      
      July 27, 2011 @ 4:28 am | Reply
      • iKocka:

        I don’t like that you keep your node rebooting every fee days, especially without any notice or apology.

        July 27, 2011 @ 8:31 am | Reply
  10. @iKocka horrible? sorry, I only understand logs… this is my tracert from my SSD VPS to arrive to NY. This is perfect!!

    [root@cluster003 ~]# tracert 198.32.118.106
    traceroute to 198.32.118.106 (198.32.118.106), 30 hops max, 40 byte packets
    1 46.105.111.253 (46.105.111.253) 0.352 ms * *
    2 rbx-g2-a9.fr.eu (178.33.100.113) 0.689 ms 0.762 ms 1.143 ms
    3 ldn-5-6k.uk.eu (91.121.131.178) 4.216 ms * *
    4 paix.ny.routers.ovh.net (198.32.118.106) 75.225 ms 75.332 ms 75.458 ms

    July 27, 2011 @ 4:18 am | Reply
    • iKocka:

      I’m talking about single thread connection speeds which are in KB/s. NY is not the only city in USA.

      July 27, 2011 @ 8:30 am | Reply
  11. Ztc:

    Very appealing, would have loved to try it but the port speed is really holding me back on this one…

    July 28, 2011 @ 7:46 pm | Reply
  12. José Carlos:

    hi,

    I wonder how long it takes to send the server data and IP, it has signed a two-day plan with vpsdeploy.com and so far have no answer.

    Thanks

    October 10, 2011 @ 2:26 pm | Reply
  13. I see U’re running VMs on SSD.. like me (OCZ Vertex3, Intel 320 300GB coming soon).
    Kernel 2.6.32 doesn’t support TRIM. You need at least 2.6.33..

    January 3, 2012 @ 9:41 pm | Reply

Leave a Reply

Some notes on commenting on LowEndBox:

  • Do not use LowEndBox for support issues. Go to your hosting provider and issue a ticket there. Coming here saying "my VPS is down, what do I do?!" will only have your comments removed.
  • Akismet is used for spam detection. Some comments may be held temporarily for manual approval.
  • Use <pre>...</pre> to quote the output from your terminal/console, or consider using a pastebin service.

Your email address will not be published. Required fields are marked *